{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:WNJNGGYTSBECVZABA3U7BTQEX2","short_pith_number":"pith:WNJNGGYT","schema_version":"1.0","canonical_sha256":"b352d31b1390482ae40106e9f0ce04beb6a7125be2c93fb31d13eb272b701276","source":{"kind":"arxiv","id":"1809.10341","version":2},"attestation_state":"computed","paper":{"title":"Deep Graph Infomax","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.IT","cs.LG","cs.SI","math.IT"],"primary_cat":"stat.ML","authors_text":"Petar Veli\\v{c}kovi\\'c, Pietro Li\\`o, R Devon Hjelm, William Fedus, William L. Hamilton, Yoshua Bengio","submitted_at":"2018-09-27T04:53:24Z","abstract_excerpt":"We present Deep Graph Infomax (DGI), a general approach for learning node representations within graph-structured data in an unsupervised manner. DGI relies on maximizing mutual information between patch representations and corresponding high-level summaries of graphs---both derived using established graph convolutional network architectures. The learnt patch representations summarize subgraphs centered around nodes of interest, and can thus be reused for downstream node-wise learning tasks. In contrast to most prior approaches to unsupervised learning with GCNs, DGI does not rely on random wa"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"1809.10341","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-09-27T04:53:24Z","cross_cats_sorted":["cs.IT","cs.LG","cs.SI","math.IT"],"title_canon_sha256":"9aa0538b52533f296c9629bc7e776d7be16f9ff26fd267d4cae63c8322148b37","abstract_canon_sha256":"b4c492c4c54ca029226355776e23809ad8d6b85353eab78b673149bdbb3a79d4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:57:46.577093Z","signature_b64":"CrlI0Nl7+1Dn940ZmcFCJG0p6CRRw1X2ikSUE0ae7UQ9XyjEtBNhLOzFRN6WlyS15us/NSBhGesNqaDLk2f+CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b352d31b1390482ae40106e9f0ce04beb6a7125be2c93fb31d13eb272b701276","last_reissued_at":"2026-05-17T23:57:46.576429Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:57:46.576429Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Deep Graph Infomax","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.IT","cs.LG","cs.SI","math.IT"],"primary_cat":"stat.ML","authors_text":"Petar Veli\\v{c}kovi\\'c, Pietro Li\\`o, R Devon Hjelm, William Fedus, William L. Hamilton, Yoshua Bengio","submitted_at":"2018-09-27T04:53:24Z","abstract_excerpt":"We present Deep Graph Infomax (DGI), a general approach for learning node representations within graph-structured data in an unsupervised manner. DGI relies on maximizing mutual information between patch representations and corresponding high-level summaries of graphs---both derived using established graph convolutional network architectures. The learnt patch representations summarize subgraphs centered around nodes of interest, and can thus be reused for downstream node-wise learning tasks. In contrast to most prior approaches to unsupervised learning with GCNs, DGI does not rely on random wa"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1809.10341","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"1809.10341","created_at":"2026-05-17T23:57:46.576527+00:00"},{"alias_kind":"arxiv_version","alias_value":"1809.10341v2","created_at":"2026-05-17T23:57:46.576527+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1809.10341","created_at":"2026-05-17T23:57:46.576527+00:00"},{"alias_kind":"pith_short_12","alias_value":"WNJNGGYTSBEC","created_at":"2026-05-18T12:33:01.666342+00:00"},{"alias_kind":"pith_short_16","alias_value":"WNJNGGYTSBECVZAB","created_at":"2026-05-18T12:33:01.666342+00:00"},{"alias_kind":"pith_short_8","alias_value":"WNJNGGYT","created_at":"2026-05-18T12:33:01.666342+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":12,"internal_anchor_count":8,"sample":[{"citing_arxiv_id":"2605.23241","citing_title":"RelPrism: A Multi-Faceted Pre-training Framework with Self-Generated Tasks for Relational Databases","ref_index":45,"is_internal_anchor":true},{"citing_arxiv_id":"2408.13471","citing_title":"Disentangled Generative Graph Representation Learning","ref_index":7,"is_internal_anchor":true},{"citing_arxiv_id":"2605.21600","citing_title":"ConTact: Contact-First Antibody CDR Design via Explicit Interface Reasoning","ref_index":180,"is_internal_anchor":true},{"citing_arxiv_id":"2605.21610","citing_title":"AgForce Enables Antigen-conditioned Generative Antibody Design","ref_index":180,"is_internal_anchor":true},{"citing_arxiv_id":"2605.21485","citing_title":"EvoStruct: Bridging Evolutionary and Structural Priors for Antibody CDR Design via Protein Language Model Adaptation","ref_index":180,"is_internal_anchor":true},{"citing_arxiv_id":"2605.16088","citing_title":"Multi-level Self-supervised Pretraining on Compositional Hierarchical Graph for Molecular Property Prediction","ref_index":30,"is_internal_anchor":true},{"citing_arxiv_id":"2605.19916","citing_title":"Fast and Featureless Node Representation Learning with Partial Pairwise Supervision","ref_index":4,"is_internal_anchor":true},{"citing_arxiv_id":"2605.14464","citing_title":"From Schema to Signal: Retrieval-Augmented Modeling for Relational Data Analytics","ref_index":42,"is_internal_anchor":true},{"citing_arxiv_id":"2604.14204","citing_title":"Disentangled Dual-Branch Graph Learning for Conversational Emotion Recognition","ref_index":28,"is_internal_anchor":false},{"citing_arxiv_id":"2604.06928","citing_title":"Leveraging LLMs and Heterogeneous Knowledge Graphs for Persona-Driven Session-Based Recommendation","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2604.15699","citing_title":"Graph self-supervised learning based on frequency corruption","ref_index":52,"is_internal_anchor":false},{"citing_arxiv_id":"2604.15704","citing_title":"Intent Propagation Contrastive Collaborative Filtering","ref_index":22,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WNJNGGYTSBECVZABA3U7BTQEX2","json":"https://pith.science/pith/WNJNGGYTSBECVZABA3U7BTQEX2.json","graph_json":"https://pith.science/api/pith-number/WNJNGGYTSBECVZABA3U7BTQEX2/graph.json","events_json":"https://pith.science/api/pith-number/WNJNGGYTSBECVZABA3U7BTQEX2/events.json","paper":"https://pith.science/paper/WNJNGGYT"},"agent_actions":{"view_html":"https://pith.science/pith/WNJNGGYTSBECVZABA3U7BTQEX2","download_json":"https://pith.science/pith/WNJNGGYTSBECVZABA3U7BTQEX2.json","view_paper":"https://pith.science/paper/WNJNGGYT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1809.10341&json=true","fetch_graph":"https://pith.science/api/pith-number/WNJNGGYTSBECVZABA3U7BTQEX2/graph.json","fetch_events":"https://pith.science/api/pith-number/WNJNGGYTSBECVZABA3U7BTQEX2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WNJNGGYTSBECVZABA3U7BTQEX2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WNJNGGYTSBECVZABA3U7BTQEX2/action/storage_attestation","attest_author":"https://pith.science/pith/WNJNGGYTSBECVZABA3U7BTQEX2/action/author_attestation","sign_citation":"https://pith.science/pith/WNJNGGYTSBECVZABA3U7BTQEX2/action/citation_signature","submit_replication":"https://pith.science/pith/WNJNGGYTSBECVZABA3U7BTQEX2/action/replication_record"}},"created_at":"2026-05-17T23:57:46.576527+00:00","updated_at":"2026-05-17T23:57:46.576527+00:00"}